No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Machine Learning Based Approach to Detect Adulteration in Turmeric Using RGB and Thermal Images
ResearchGate has not been able to resolve any citations for this publication.
We are frequently exposed to potentially harmful microbes of various types on a daily basis. Our immune system is an amazing collection of unique organs and cells that defends us from hazardous germs as well as certain diseases. It plays a crucial role in protecting the body against external invaders, including bacteria, viruses, and parasites. Maintaining a healthy immune system requires consuming a balanced diet that provides a variety of macro‐ and micronutrients. By consuming sufficient amounts of water, minerals such as zinc and magnesium, micronutrients, herbs, and foods rich in vitamins C, D, and E, and adopting a healthy lifestyle, one can enhance their health and immunity, and prevent infections. This article provides a comprehensive review of the scientific literature on common foods known for their potential to boost human immunity. The review begins by discussing the various components of the immune system and their functions. It then delves into the current understanding of how nutrition can influence immune response, highlighting the importance of a well‐balanced diet in supporting optimal immune function. The article presents an extensive analysis of a range of common foods that have been studied for their immune‐boosting properties. These foods include fruits, vegetables, whole grains, and animal‐based foods. Each food category is explored in terms of its specific nutrients and bioactive compounds that contribute to immune support. Foods such as milk, eggs, fruits, leafy greens, and spices like onion, garlic, and turmeric contain beneficial compounds that can enhance the immune system's function, activate and inhibit immune cells, and interfere with multiple pathways that eventually lead to improved immune responses and defense. The available literature on the issue was accessed via online resources and evaluated thoroughly as a methodology for preparing this manuscript.
Food adulteration occurs globally, in many facets, and affects almost all food commodities. Adulteration is not just a crucial economic problem, but it may also lead to serious health problems for consumers. Turmeric (Curcuma longa) is a world-class spice commonly contaminated with various chemicals and colors. It has also been used extensively in many Asian curries, sauces, and medications. Different traditional approaches, such as chemical and physical methods, are available for detecting adulterants in turmeric. These approaches are rather time-consuming and inaccurate methods. Therefore, it is of utmost importance to identify the adulterants in turmeric accurately and instantly. A cloud-based system was developed to detect adulteration in adulterated turmeric. The dataset consists of spectral images of turmeric with tartrazine-colored rice flour adulterant. Adulterants in weight percentages of 0%, 5%, 10%, and 15% were mixed with turmeric. A convolutional neural network (CNN) was implemented to detect adulteration, which achieved 100% accuracy for training and 94.35% accuracy for validation. The deep CNN (DCNN) models, namely, VGG16, DenseNet201, and MobileNet, were implemented to detect adulteration. The proposed CNN model outperforms DCNN models in terms of accuracy and layers. The CNN model is deployed to the platform as a service (PaaS) cloud. The deployed model link can be accessed using a smartphone. Uploading the adulterated turmeric image to a cloud link can analyze and detect adulteration.
Turmeric has faced authenticity issues as instances of economic-adulterations to reduce the cost. We used carbon-14 and HPLC analyses as complementary methods to verify “all-natural” label claims of commercial dietary supplements containing turmeric ingredients. A high percentage of curcumin-to-curcuminoids value was used as an indicator to imply the presence of synthetic curcumin. However, using the HPLC method alone did not provide direct evidence of curcuminoids’ natural origin, whereas using only the carbon-14 method cannot test for potency label claims and determine which constituent(s) contain ¹⁴C radiocarbon. By analyzing results from both methods, a significant correlation between the percentage of curcumin-to-curcuminoids and % biobased carbon (Pearson’s r = -0.875, p < 0.001) indicated that synthetic curcumin was greatly attributed to determined synthetic ingredients. Only four out of the 14 samples analyzed supported authentic label claims. This orthogonal testing strategy showed its potential for the quality control of turmeric products.
Turmeric (Curcuma longa) is an important condiment used in the culinary of several countries to spice and give a more intense yellow color to food. The importance of this root has gained more attention due to the presence of bioactive compounds known as curcuminoids (the main class of phenolic compounds found in turmeric). The health benefits attributed to curcuminoids are mainly linked to curcumin, the major compound among curcu-minoids. Scientific evidence from pre-clinical and clinical trials indicate that turmeric extracts (rich in curcumin) and curcumin can effectively improve the status of subjects by reducing the risk of cardiovascular diseases and diabetes as well as assisting in the management of illness. The present review aims to highlight the use of green extraction technologies to obtain curcuminoid-rich extracts and the health benefits associated with the consumption of turmeric extracts and curcumin (as dietary supplements) against cardiovascular diseases, diabetes, metabolic syndrome, arthritis, and mental disorders at clinical trial level. The current knowledge about the development of functional foods with curcumin is also discussed.
Synthetic colorants such as metanil yellow, lead chromate, Acid orange 7, Sudan red; rhizomes of related Curcuma sp. besides spent turmeric, starch, chalk and yellow soapstone are the main adulterants in traded turmeric while synthetic curcumin is an adulterant of natural curcumin. Both branded products as well as the produce from the unorganized sector are found adulterated. The adulterants, added either to increase the bulk, improve the colour and appearance or enhance the profit margin, often result in corroding the biological efficacy of the commodity and eroding the public impression besides posing health risks to the consumers. Various physical, chemical and PCR based methods are available to detect the adulterants in traded turmeric. While chemical methods are suited to detect the synthetic adulterants and spent turmeric, DNA based methods are the best options for detecting the biological adulterants (except spent turmeric) in the commodity. Along with adopting a supply chain system and quality linked pricing in turmeric trade, commercial adulteration diagnostic kits, if they can be developed and deployed, will be a very convenient way to ensure the quality of the traded produce.
This paper investigates the feasibility of Fourier transform near-infrared (FT-NIR) spectroscopy, a fast and easy method based on chemometric methods to detect corn starch illegally added to turmeric powder. In this work, the pure turmeric powders were blended with corn starch to generate different concentrations (1-30%)(w/w) of starch-adulterated turmeric samples. The reflectance spectra of total of 224 samples were taken by FT-NIR spectroscopy. The exploratory data analysis was done by principal component analysis (PCA). The starch related peaks were selected by variable importance in projection (VIP) method and were explored by examination of original reflectance spectra, 1 st derivative spectra, PCA loadings and β coefficients plot of the partial least square regression (PLSR) model. The coefficient of determination (R 2) and root-mean-square error of partial least square regression (PLSR) models were found to be 0.91-0.99 and 0.23-1.3%, respectively, depending on the pre-processing techniques of spectral data. The figure of merit (FOM) of the model was found with the help of net analyte signal (NAS) theory. ARTICLE HISTORY
Yellow turmeric (Curcuma longa) is widely used for culinary and medicinal purposes, and as a dietary supplement. Due to the commercial popularity of C. longa, economic adulteration and contamination with botanical additives and chemical substances has increased. This study used FT-IR spectroscopy for identifying and estimating white turmeric (Curcuma zedoaria), and Sudan Red G dye mixed with yellow turmeric powder. Fifty replicates of yellow turmeric—Sudan Red mixed samples (1%, 5%, 10%, 15%, 20%, 25% Sudan Red, w/w) and fifty replicates of yellow turmeric—white turmeric mixed samples (10%, 20%, 30%, 40%, 50% white turmeric, w/w) were prepared. The IR spectra of the pure compounds and mixtures were analyzed. The 748 cm−1 Sudan Red peak and the 1078 cm−1 white turmeric peak were used as spectral fingerprints. A partial least square regression (PLSR) model was developed for each mixture type to estimate adulteration concentrations. The coefficient of determination (R2v) for the Sudan Red mixture model was 0.97 with a root mean square error of prediction (RMSEP) equal to 1.3%. R2v and RMSEP for the white turmeric model were 0.95 and 3.0%, respectively. Our results indicate that the method developed in this study can be used to identify and quantify yellow turmeric powder adulteration.
This article investigates the possibility of using electrical impedance spectroscopy (EIS) technique for detection and quantification of metanil yellow (MY) in turmeric powder. The observation is supported by ultraviolet–visible (UV–Vis) absorption spectroscopy and Fourier transform mid infrared (FT-MIR) spectroscopy. Variation of electrical parameters like capacitance, impedance, conductance, and current–voltage (I–V) characteristics for pure as well as adulterated turmeric are analyzed. System capacitance, conductance, and current are observed to increase, whereas the impedance values have been found to decrease with increase in MY content. Also, UV–Vis and FT-MIR spectroscopic measurements suggest the increase of absorbance with gradual increment of MY in the solution. Electrical and optical results have been physically corroborated with respect to the system internal energy. This study sought to provide a deterministic approach towards developing an EIS-based adulterant sensor for simple, rapid, economical, and precise quantification of controlled percentage weights of MY in pure turmeric powder.
Adulteration in food has been a concern since the beginning of civilization, as it not only decreases the quality of food products but also results in a number of ill effects on health. Authentic testing of food and adulterant detection of various food products is required for value assessment and to assure consumer protection against fraudulent activities. Through this review we intend to compile different types of adulterations made in different food items, the health risks imposed by these adulterants and detection methods available for them. Concerns about food safety and regulation have ensured the development of various techniques like physical, biochemical/ immunological and molecular techniques, for adulterant detection in food. Molecular methods are more preferable when it comes to detection of biological adulterants in food, although physical and biochemical techniques are preferable for detection of other adulterants in food.
Turmeric is a mild digestive, being aromatic, a stimulant and a carminative Turmeric is one of nature's most powerful healers. The active ingredient in turmeric is curcumin. Tumeric has been used for over 2500 years in India, where it was most likely first used as a dye. The medicinal properties of this spice have been slowly revealing themselves over the centuries. Long known for its anti-inflammatory properties, recent research has revealed that turmeric is a natural wonder, proving beneficial in the treatment of many different health conditions from cancer to Alzheimer's disease. An ointment base on the spice is used as an antiseptic in India. Turmeric water is an Asian cosmetic applied to impart a golden glow to the complexion. Curcumin has been shown to be active against Staphlococcus aureus (pus-producing infections). Anemia, cancer, diabetes, digestion, food poisoning, gallstones, indigestion, IBS, parasites, poor circulation, staph infections, and wounds. Turmeric decreases Kapha and so is used to remove mucus in the throat, watery discharges like leucorrhea, and any pus in the eyes, ears, or in wounds, etc. In Unani medicine, turmeric has been used for conditions such as liver obstruction and jaundice and has been applied externally for ulcers and inflammation. Roasted turmeric has been used as an ingredient of a preparation used for dysentery. Turmeric has also been used in tooth powder or paste. Turmeric has been used for many conditions in traditional medicine in India, Pakistan and Bangladesh. The rhizome is generally the part of the plant that is most widely used. It can be prepared in various ways and is reputed to alleviate asthma and coughs. Hot water extracts of the dried rhizome have been taken orally in Ayurvedic medicine to reduce inflammation. Turmeric is also regarded as a 'rasayana' herb, which is a branch of Ayurvedic medicine. Here turmeric is used to counteract ageing processes.
Ethnopharmacological relevance:
Herbal medicine value chains have generally been overlooked compared with food commodities. Not surprisingly, revenue generation tends to be weighted towards the end of the chain and consequently the farmers and producers are the lowest paid beneficiaries. Value chains have an impact both on the livelihood of producers and on the composition and quality of products commonly sold locally and globally and consequently on the consumers. In order to understand the impact of value chains on the composition of products, we studied the production conditions for turmeric (Curcuma longa) and the metabolomic composition of products derived from it. We aimed at integrating these two components in order to gain a better understanding of the effect of different value chains on the livelihoods of some producers.
Materials and methods:
This interdisciplinary project uses a mixed methods approach. Case studies were undertaken on two separate sites in India. Data was initially gathered on herbal medicine value chains by means of semi-structured interviews and non-participant observations. Samples were collected from locations in India, Europe and the USA and analysed using (1)H NMR spectroscopy coupled with multivariate analysis software and with high performance thin layer chromatography (HPTLC).
Results:
We investigate medicinal plant value chains and interpret the impact different value chains have on some aspects of the livelihoods of producers in India and, for the first time, analytically assess the chemical variability and quality implications that different value chains may have on the products available to end users in Europe. There are benefits to farmers that belonged to an integrated chain and the resulting products were subject to a higher standard of processing and storage. By using analytical methods, including HPTLC and (1)H NMR spectroscopy, it has been possible to correlate some variations in product composition for selected producers and identify strengths and weaknesses of some types of value chains. The two analytical techniques provide different and complementary data and together they can be used to effectively differentiate between a wide variety of crude drug powders and herbal medicinal products.
Conclusions:
This project demonstrates that there is a need to study the links between producers and consumers of commodities produced in so-called 'provider countries' and that metabolomics offer a novel way of assessing the chemical variability along a value chain. This also has implications for understanding the impact this has on the livelihood of those along the value chain.
The curry powder spices turmeric (Curcuma longa L.), which contains curcumin (diferuloylmethane), an orange-yellow chemical. Polyphenols are the most commonly used sources of curcumin. It combats oxidative stress and inflammation in diseases, such as hyperlipidemia, metabolic syndrome, arthritis, and depression. Most of these benefits are due to their anti-inflammatory and antioxidant properties. Curcumin consumption leads to decreased bioavailability, resulting in limited absorption, quick metabolism, and quick excretion, which hinders health improvement. Numerous factors can increase its bioavailability. Piperine enhances bioavailability when combined with curcumin in a complex. When combined with other enhancing agents, curcumin has a wide spectrum of health benefits. This review evaluates the therapeutic potential of curcumin with a specific emphasis on its approach based on molecular signaling pathways. This study investigated its influence on the progression of cancer, inflammation, and many health-related mechanisms, such as cell proliferation, apoptosis, and metastasis. Curcumin has a significant potential for the prevention and treatment of various diseases. Curcumin modulates several biochemical pathways and targets involved in cancer growth. Despite its limited tissue accumulation and bioavailability when administered orally, curcumin has proven useful. This review provides an in-depth analysis of curcumin's therapeutic applications, its molecular signaling pathway-based approach, and its potential for precision medicine in cancer and human health.
Analytical tests are commonly performed in laboratories to analyze and ensure food quality due to concerns about food adulteration. However, traditional analytical methods that rely on chemicals or equipment are often time-consuming and expensive. Therefore, we propose an efficient method for detecting starch adulterants in turmeric, which is clean, green, inexpensive, and rapid. Near-infrared (NIR) spectroscopy meets all these criteria and has a high potential for conducting routine assessments. To acquire reflectance spectra from the 900 nm–1700 nm range, we used the compact TI DLPNIRscan Nano module instead of a traditional bulky and costly spectrophotometer. Turmeric samples were adulterated with starch, ranging from 0% to 50%, and the Savitzky–Golay (SG) filter was applied to the recorded spectra. Various machine learning (ML) models were used to train and test these spectra, and the PCA approach was used to reduce the dimensionality of the data and assess its effectiveness. We have used several metrics, including R2, Root Mean Square Error (RMSEV), Mean Absolute Error (MAEV), and Leave-one-out Cross-Validation (LOOCV), to evaluate the performance of the ML models. The Extra Tree Regressor (ETR) outperformed the other models, achieving an R2 of 0.995, an RMSEV of 1.056 mg (W/W), an MAE of 0.597 mg (W/W), a LOOCV R2 of 0.994, and a LOOCV RMSEV of 1.038 mg (W/W).
Turmeric is widely used as a health supplement and foodstuff in South East Asian countries because of its medicinal benefits. Like several other plants and peppers, turmeric is prone to exploitation because of its economic value, rising consumer need, and essential food element that adds colour and flavour. Due to this, quick and comprehensive testing processes are needed to detect adulterants in turmeric. In this study, pure turmeric powders were mixed with starch in proportions ranging from 0 to 50% with a 1% variation to obtain different combinations. Reflectance spectra of pure turmeric and starch mixed samples were recorded using a JASCO-V770 spectrometer from 400 to 2050 nm. The recorded spectra were pre-processed using a Multiplicative Scatter Correction (MSC) and Standard Normal Variate (SNV). The Savitzky-Golay (SG) filter was initially applied to these original (X), MSC, and SNV-corrected spectra. Secondly, the Extra Tree Regressor (ETR) feature selection method was employed to select the best features. Finally, principal component analysis (PCA) was used to reduce the dimension of the selected features. The stacked generalization method was applied to improve the performance of this work. Both regressors and classifier stacking techniques have been tested with different classification and regression methods. The K-Nearest Neighbours (KNN), Decision Tree (DT), and Random Forest (RF) models were used as base learners, and Logistic Regression (LRC) was used as a meta-model for classification and Linear Regression (LR) for regression analysis. The proposed method achieved the best regression performance with r2 of 0.999, Root Mean Square Error (RMSE) of 0.206, Ratio of Performance to Deviation (RPD) of 73.73, and Range Error Ratio (RER) of 480.58, whereas 100% F1 score and Matthew’s Correlation Coefficient (MCC) classification performance.
Introduction
Process analytical technology (PAT) guidance is implemented in the quality assurance of phytocompounds to achieve the Industry 4.0 concept. Near-infrared (NIR) and Raman spectroscopies are feasible for rapid, reliable quantitative analysis through transparent packaging without removing the samples from their original containers. These instruments can serve PAT guidance.
Objective
This study aimed to develop online portable NIR and Raman spectroscopic methods for quantifying total curcuminoids in turmeric samples through a plastic bag. The method mimicked an in-line measurement mode in PAT compared with placing samples into a glass vessel (at-line mode).
Materials and methods
Sixty-three curcuminoid standard-spiked samples were prepared. Then, 15 samples were randomly selected as fixed validation samples, and 40 of the 48 remaining samples were chosen as calibration set. The results obtained from the partial least square regression (PLSR) models constructed by using the spectra acquired from NIR and Raman were compared with the reference values from high-performance liquid chromatography (HPLC).
Results
The optimum PLSR model of at-line Raman was achieved with three latent variables and a root mean square error of prediction (RMSEP) of 0.46. Meanwhile, the PLSR model of at-line NIR with one latent variable offered an RMSEP of 0.43. For the in-line mode, PLSR models created from Raman and NIR spectra had one latent variable with RMSEP of 0.49 and 0.42, respectively. The R2 values for prediction were 0.88–0.92.
Conclusion
The models established from the spectra from portable NIR and Raman spectroscopic devices with the appropriate spectral pretreatments allowed the determination of total curcuminoid contents through plastic bag.
In the present contribution, visible and short wavelengths of near infrared hyperspectral imaging (VIS-SWNIR-HSI) combined with different chemometric techniques is proposed as a novel technique for turmeric authentication and multiple adulterants (corn flour, rice flour, starch, wheat flour, and zedoary) detection. In this regard, twenty-three samples of turmeric were collected as whole rhizomes or powdered from seven countries and then their VIS-SWNIR hyperspectral images were obtained in 400-1000 nm using SPECIM IQ HSI device. Two multivariate resolution techniques of multivariate curve resolution-alternating least squares (MCR-ALS) and mean-field independent component analysis (MF-ICA) were used to extract pure spatial and spectral profiles of the components, and their results were compared by projecting their solutions in the area of feasible solutions (AFSs). Then, the distribution maps of turmeric component obtained using MCR-ALS and MF-ICA were used for authentication. Principal component analysis (PCA) was used to find the pattern of authentic samples using their distribution maps. Additionally, data-driven soft independent modeling of class analogy (DD-SIMCA) was employed to find boundary between authentic and adulterated turmeric samples. On this matter, good class modelling results with sensitivity of 95% and specificity of 100% were obtained. Finally, partial least squares-discriminant analysis (PLS-DA) was utilized for discrimination of the of adulternats and their in binary and multi-class classification modes. On this matter, PLS-DA accuracies were acceptable for binary and mixed samples which confirmed the validity of the proposed method.
Adulterants can cause different health hazards upon prolonged consumption, but it is difficult to detect with human eyes. Non‐destructive turmeric adulteration detection is a challenging research area. The existing adulteration detection processes are largely instrumental and analytical with high accuracy but include limitations like long testing time, expensiveness, and lack of mobility. This work reports a new computer vision framework, which can simultaneously detect the presence of adulteration and predict the possible percentage of adulteration addressing the stated limitations. The scope has been remained to screening of Sudan dye‐I adulteration in turmeric powder. An in‐house database prepared with images of pure and adulterated turmeric powder samples has been used for experimentation. Random Forest algorithm has been employed for both classification and prediction. The model has been validated with standard internal and external validation methods to assess the stability and generalization potential of the model to avoid over‐ and under‐fitting problems. The results of classification show that the presented framework can provide more than 99% accuracy in detection while high correlation coefficient (R2) value in the tune of .99 for prediction. The novelty of the work is its simple histogram‐based color feature extraction, development of ensemble Random Forest prediction model that resulted in high accuracy and development of a faster, non‐invasive, less‐expensive, and validated screening method for adulterated turmeric powder that can be considered as a potential immediate screening method in the supply chain of powdered spices prior to confirmatory testing methods following two‐tiered food fraud testing approach.
Turmeric (Curcuma longa) is a popular food ingredient which is widely used in powdered form. Despite different food and medicinal advantages it is often adulterated. Metanil yellow (MET) is one such synthetic chemical which can be easily mixed with turmeric powder and such mixing is difficult to detect. This paper presents a computer vision framework using the potential of deep neural network towards detection of MET adulteration in turmeric powder and random forests regressor to predict the possible amount of adulterant. An in‐house database consisting of features from turmeric images of five variants of pure and adulterated turmeric powder has been used for experimentations. A new frequency domain annular‐mean filter‐based feature extraction has been used. The results show the potential of the presented method that can perform with more than 98% accuracy in both identification and prediction tasks. The reported technique can be considered as a motivating step towards development of a non‐invasive and low‐cost mobile device towards food adulteration detection in future.
In this research, 56 samples of pure honey have been mixed with different concentrations of rice syrup simulating a set of adulterated samples. A thermographic camera was used to extract data regarding the thermal development of the honey. The resulting infrared images were processed via convolutional neural networks (CNNs), a subset of algorithms within deep learning. The CNNs have been trained and optimized using these images to detect the commonly elusive rice syrup in honey in concentrations as low as 1% in weight, as well as quantify it. Finally, the model was successfully validated using images which were initially isolated from the training database. The result was an algorithm capable of identifying adulterated honey from different floral origins and quantifying rice syrup with accuracies of 95% and 93%, respectively. Therefore, CNNs have complemented the thermographic analysis and have shown to be a compelling tool for the control of food quality, thanks to traits such as high sensitivity, speed, and being independent of highly specialized personnel.
Fourier transform near infrared spectroscopy (FT-NIR) in diffuse reflectance mode was used for the rapid estimation of curcumin, starch and moisture contents in turmeric samples. Thirty samples each of fingers and bulbs from varieties ‘Erode local’ and ‘Salem local’ (n = 120) were used for the study. Calibration models were developed and evaluated to describe the relationship between the three quality attributes with the NIR spectra of the turmeric powder. NIR reflectance spectra were acquired for each turmeric sample at a resolution of 8 cm ⁻¹ over a wave number range of 12,500 to 3600 cm ⁻¹ . Vector normalization, first derivative and first derivative plus vector normalization were used as spectral pre-processing options. The relationship between the acquired spectra of turmeric samples and the quality attributes was examined through partial least square (PLS) regression algorithm. First derivative plus vector normalization technique predicted curcumin content with best accuracy with lowest root mean square error of cross validation (RMSECV) of 0.178% and maximum correlation coefficient for validation plots (R ² = 91.9). Vector normalization technique predicted the starch and moisture content with RMSECV and R ² value of 0.076%, 96.8 and 0.032%, 81.1 respectively. The results demonstrated that FT-NIR could be used as a rapid technique for quantification of curcumin, starch and moisture content in turmeric rhizomes for online grading in spice processing. © 2019 Asian Agricultural and Biological Engineering Association
Starch adulteration in turmeric samples through multivariate analysis with infrared spectroscopy
- I Y L De Macêdo
- IYL de Macêdo
Digital image-based detection of wheat flour adulteration in turmeric powder: a deep learning approach Google Scholar
- D Meena
- N Tiwari
- Mishra
- R Prakash